patchwork_csv_utils 0.1.22-x86_64-linux → 0.1.23-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5b284ba3c70cec13c91ba655fb13145182d8da5bcc80c018a388eb630bc27865
-  data.tar.gz: 4bc87184786c705c5fe022e169bcd9f17243314f96a3c4a5c8132ca45a11330d
+  metadata.gz: 7dbd4e8e3e38f09e1b1cb979b7680150727ca7d8035d6562377f11abf3277b43
+  data.tar.gz: 338f7001ce3fbf172b2a5eb5d4acf43554f500d9f43b38eb21fab69ba721cbf1
 SHA512:
-  metadata.gz: 75133438e59bf485be49345ca0f9e6cb3ec3c60a85036069b2a6e0757bb9d326cc989f4d7ed822993ad1b50bcbea4e19f7e32f86dc4e995ff0964e94e3c8d092
-  data.tar.gz: c91c751ac4af03e02628fff0616c7da7d64d57bf57bec384a5799869b7f5fda1edb4550b80c7761f56227b83f6349eddf9b2ae0f8f4a6b80b75046a4a5c3645b
+  metadata.gz: 278daadccc1ba57cdcaab7f19b7a0fc0695ca9aca00a71923fae359fd1f5d5707f9c3423ed7d8c426c6ae21f1123e442253fad3cd3ae55b15f5e0e6493cfad3b
+  data.tar.gz: 749d3e76b5b359590777c96961c59c0b1c9651e7cefce16f2a0300cbc9121ed7e4393ea5dd80ae82fa7caca42b9c4492e29a656a1c08bdba48c56de9fed9a603

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.22)
+    patchwork_csv_utils (0.1.23)
 
 GEM
   remote: https://rubygems.org/

data/ext/csv_utils/src/lib.rs

@@ -9,7 +9,7 @@ pub mod utils;
 fn init() -> Result<(), magnus::Error> {
     let module = define_module("CsvUtils")?;
     module.define_singleton_method("dedup", function!(dedup, 4))?;
-    module.define_singleton_method("to_csv", function!(to_csv, 7))?;
-    module.define_singleton_method("transform_csv", function!(transform_csv, 7))?;
+    module.define_singleton_method("to_csv", function!(to_csv, 8))?;
+    module.define_singleton_method("transform_csv", function!(transform_csv, 8))?;
     Ok(())
 }

data/ext/csv_utils/src/utils/csv.rs

@@ -1,10 +1,10 @@
-use chrono::{NaiveDate, NaiveDateTime, NaiveTime, Utc};
+use chrono::{NaiveDateTime, NaiveTime, Utc};
 use csv::{Reader, StringRecord, Writer};
 use magnus::{Error, RArray, Ruby};
 use std::collections::HashMap;
 use std::fs::File;
 
-use crate::utils::{check_mandatory_headers, create_header_map, headers_as_byte_record, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, to_datetime_error, FileExtension};
+use crate::utils::{check_mandatory_headers, correct_datetime, create_header_map, headers_as_byte_record, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, string_to_datetime, to_datetime_error, FileExtension};
 
 pub fn transform_csv(ruby: &Ruby,
                      csv_path: String,
@@ -13,11 +13,15 @@ pub fn transform_csv(ruby: &Ruby,
                      mandatory_headers: RArray,
                      status_exclusions: RArray,
                      expected_trust_name: String,
-                     is_streamed_file: bool) -> magnus::error::Result<()> {
+                     is_streamed_file: bool,
+                     earliest_start_date: Option<String>) -> magnus::error::Result<()> {
     if !csv_path.has_extension(&["csv"]) {
         return Err(Error::new(ruby.exception_standard_error(), "csv_path must be a csv file".to_string()));
     }
 
+    let start_date = earliest_start_date
+        .and_then(|date_str| string_to_datetime(&date_str));
+
     let exclusions = RArray::to_vec(exclusions)?;
     let status_exclusions = RArray::to_vec(status_exclusions)?;
     let mandatory_headers: Vec<String> = RArray::to_vec(mandatory_headers)?;
@@ -50,6 +54,7 @@ pub fn transform_csv(ruby: &Ruby,
 
     for (ri, record) in mandatory_records.iter().enumerate() {
 
+        if skip_rows_before_start_date(&start_date, &record, &date) { continue; }
         if skip_excluded_rows(request_id, &status, &record, &exclusions) { continue; }
         if skip_excluded_status_rows(&status, &record, &status_exclusions) { continue; }
         if has_empty_row_skip(&record) { continue; }
@@ -155,22 +160,23 @@ fn skip_excluded_rows(request_id: &usize, status: &Option<&usize>, r: &StringRec
     exclusions.contains(&value.to_string())
 }
 
+fn skip_rows_before_start_date(&start_date: &Option<NaiveDateTime>, r: &StringRecord, date_index: &usize) -> bool {
+    if let Some(start_date) = start_date {
+        if let Some(date_str) = r.get(*date_index) {
+            if let Some(date) = string_to_datetime(date_str) {
+                return date <= start_date;
+            }
+        }
+    }
+    false
+}
+
 fn skip_excluded_status_rows(status: &Option<&usize>, r: &StringRecord, exclusions: &Vec<String>) -> bool {
     status
         .map(|index| exclusions.contains(&r[*index].to_string()))
         .unwrap_or(false)
 }
 
-fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
-    let maybe_correct = correct_datetime(s);
-    if maybe_correct.is_some() { return maybe_correct; }
-
-    NaiveDate::parse_from_str(s, "%d-%b-%y").ok().map(|d| d.and_hms_opt(0, 0, 0)).flatten()
-}
-
-fn correct_datetime(s: &str) -> Option<NaiveDateTime> {
-    NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S").ok()
-}
 
 fn string_to_time(s: &str) -> Option<NaiveTime> {
     NaiveTime::parse_from_str(s, "%H:%M").ok()

data/ext/csv_utils/src/utils/mod.rs

@@ -4,6 +4,7 @@ use std::ffi::OsStr;
 use std::path::Path;
 use ::csv::{ByteRecord, StringRecord};
 use magnus::Ruby;
+use chrono::{NaiveDate, NaiveDateTime};
 
 pub mod csv;
 pub mod dedup;
@@ -83,3 +84,19 @@ impl<P: AsRef<Path>> FileExtension for P {
     }
 }
 
+pub fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
+    let maybe_correct = correct_datetime(s);
+    if maybe_correct.is_some() { return maybe_correct; }
+
+    // Try YYYY-MM-DD format
+    if let Ok(date) = NaiveDate::parse_from_str(s, "%Y-%m-%d") {
+        return date.and_hms_opt(0, 0, 0);
+    }
+
+    NaiveDate::parse_from_str(s, "%d-%b-%y").ok().map(|d| d.and_hms_opt(0, 0, 0)).flatten()
+}
+
+pub fn correct_datetime(s: &str) -> Option<NaiveDateTime> {
+    NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S").ok()
+}
+

data/ext/csv_utils/src/utils/xls.rs

@@ -6,7 +6,7 @@ use calamine::{open_workbook_auto, Data, DataType, Range, Reader};
 use chrono::{NaiveDateTime, Timelike, Utc};
 use magnus::{RArray, Ruby};
 
-use crate::utils::{check_mandatory_headers, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, to_datetime_error, FileExtension};
+use crate::utils::{check_mandatory_headers, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, string_to_datetime, to_datetime_error, FileExtension};
 
 pub fn to_csv(ruby: &Ruby, xls_path: String,
               target_path: String,
@@ -14,7 +14,8 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
               mandatory_headers: RArray,
               status_exclusions: RArray,
               expected_trust_name: String,
-              is_streamed_file: bool
+              is_streamed_file: bool,
+              earliest_start_date: Option<String>
 ) -> magnus::error::Result<()> {
     if !xls_path.has_extension(&["xls","xlsx"]) {
         return Err(magnus::Error::new(ruby.exception_standard_error(), "xls_path must be an xls or xlsx file".to_string()));
@@ -23,6 +24,9 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
     let exclusions = RArray::to_vec(exclusions)?;
     let mandatory_headers: Vec<String> = RArray::to_vec(mandatory_headers)?;
     let status_exclusions = RArray::to_vec(status_exclusions)?;
+    
+    let start_date = earliest_start_date
+        .and_then(|date_str| string_to_datetime(&date_str));
 
     let mut workbook = open_workbook_auto(&xls_path)
         .map_err(|e| magnus_err(ruby, e, format!("could not open workbook: {}", xls_path).as_str()))?;
@@ -41,7 +45,7 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
     let csv_out_file = File::create(target_path.clone()).map_err(|e| magnus_err(ruby, e, format!("could not create csv file: {}", target_path).as_str()))?;
     let mut dest = BufWriter::new(csv_out_file);
 
-    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list, status_exclusions, expected_trust_name, is_streamed_file)
+    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list, status_exclusions, expected_trust_name, is_streamed_file, start_date)
 }
 
 fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
@@ -50,7 +54,8 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
                        headers_list: Vec<String>,
                        status_exclusions: Vec<String>,
                        expected_trust_name: String,
-                       is_streamed_file: bool) -> magnus::error::Result<()> {
+                       is_streamed_file: bool,
+                       start_date: Option<NaiveDateTime>) -> magnus::error::Result<()> {
     let n = mandatory_headers.len() - 1;
     let request_id = header_map.get("Request Id").ok_or(missing_header(ruby, "Request Id"))?;
     let date = header_map.get("Date").ok_or(missing_header(ruby, "Date"))?;
@@ -66,6 +71,7 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
     for (ri, r) in mandatory_rows.into_iter().enumerate() {
         let mut date_value = Utc::now().naive_utc();
 
+        if skip_rows_before_start_date(&start_date, &r, &date) { continue; }
         if skip_excluded_rows(&request_id, &status, &r, &exclusions) { continue; }
         if skip_excluded_status_rows(&status, &r, &status_exclusions) { continue; }
         if skip_empty_rows(&r) { continue; }
@@ -214,6 +220,27 @@ fn skip_rows_with_no_request_id(request_id: &usize, r: &Vec<&Data>) -> bool {
     r[*request_id] == &Data::Empty
 }
 
+fn skip_rows_before_start_date(start_date: &Option<NaiveDateTime>, r: &Vec<&Data>, date_index: &usize) -> bool {
+    if let Some(start_date) = start_date {
+        if let Some(date_data) = r.get(*date_index) {
+            match date_data {
+                Data::DateTime(d) => {
+                    if let Some(date) = d.as_datetime() {
+                        return date <= *start_date;
+                    }
+                }
+                Data::DateTimeIso(s) => {
+                    if let Some(date) = string_to_datetime(s) {
+                        return date <= *start_date;
+                    }
+                }
+                _ => {}
+            }
+        }
+    }
+    false
+}
+
 fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveDateTime) -> NaiveDateTime {
     NaiveDateTime::new(t1.date(), t2.time())
 }

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.22'
+  VERSION = '0.1.23'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.22
+  version: 0.1.23
 platform: x86_64-linux
 authors:
 - kingsley.hendrickse